Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7447. Min Act: -0.0001

Data Index: 1451320 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8547. Min Act: -0.0001

Data Index: 1586604 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1609001 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.6506. Min Act: -0.0001

Data Index: 1392290 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.6430. Min Act: -0.0001

Data Index: 1561619 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5960. Min Act: -0.0001

Data Index: 1388545 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5883. Min Act: -0.0001

Data Index: 1599677 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5353. Min Act: -0.0001

Data Index: 1421519 (Python Code)

Max Activating Token Index: 342

Text #8

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5716. Min Act: -0.0001

Data Index: 1371162 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1448110 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5034. Min Act: -0.0001

Data Index: 1396899 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5020. Min Act: -0.0001

Data Index: 1524202 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5709. Min Act: -0.0001

Data Index: 1514976 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1514034 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5296. Min Act: -0.0001

Data Index: 1477076 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1360365 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1551464 (Python Code)

Max Activating Token Index: 406

Text #17

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5204. Min Act: -0.0001

Data Index: 1496635 (Python Code)

Max Activating Token Index: 334

Text #18

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4593. Min Act: -0.0001

Data Index: 1483333 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5495. Min Act: -0.0001

Data Index: 1613210 (Python Code)

Max Activating Token Index: 380